diff options
Diffstat (limited to 'Code/download_and_map.py')
| -rw-r--r-- | Code/download_and_map.py | 5 |
1 files changed, 2 insertions, 3 deletions
diff --git a/Code/download_and_map.py b/Code/download_and_map.py index 3f6e14b..c21e114 100644 --- a/Code/download_and_map.py +++ b/Code/download_and_map.py @@ -1,7 +1,6 @@ # Usage: python dowload_and_map.py # python download_and_map.py run_ids.txt # -# Edit DAILY_DOWNLOAD_NUMBER and MIN_FILE_SIZE # # This program checks RNA_SEQ_INFO_FILE for not yet downloaded, *public* RNA-seq data, make a list of them, download and map using Salmon. It is very important to prepare # RNA_SEQ_INFO_FILE (see parse_end_xlm.py). In fact, only first column of RNA_SEQ_INFO_FILE is required in this file, that is a list of RNA-seq IDs. @@ -25,8 +24,6 @@ from datetime import datetime ########################################################################################## from configure import DAILY_MAP_NUMBER, MIN_FASTQ_FILE_SIZE, RNA_SEQ_INFO_FILE, DOWNLOADED_SRA_ID_LOG_FILE, IGNORED_SRA_ID_LOG_FILE, UPDATE_NETWORK_LOG_FILE, MAPPED_RDATA_DIR, RAW_RDATA_DIR, SALMON_MAP_RESULT_DIR -FASTQ_DUMP_PATH = '/home/hui/software/sratoolkit/sratoolkit.2.8.0-ubuntu64/bin/fastq-dump' - ########################################################################################## def glob_files(directory, pattern): @@ -229,8 +226,10 @@ def download_and_map_data(lst, daily_map_num, dest): return downloaded_files, map_list + def download_data2(lst, dest): ''' Download data from SRA, slow ''' + FASTQ_DUMP_PATH = '/home/hui/software/sratoolkit/sratoolkit.2.8.0-ubuntu64/bin/fastq-dump' if not os.path.exists(FASTQ_DUMP_PATH): print('%s not exists.' % (FASTQ_DUMP_PATH)) sys.exit() |